| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9850746268656716, | |
| "eval_steps": 500, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 52.45830311602043, | |
| "learning_rate": 5e-06, | |
| "loss": 2.2259, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 84.15457972619473, | |
| "learning_rate": 1.9941379571543597e-05, | |
| "loss": 2.1099, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 34.75504319363182, | |
| "learning_rate": 1.796093065705644e-05, | |
| "loss": 2.0145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 12.32508429196908, | |
| "learning_rate": 1.3701381553399147e-05, | |
| "loss": 1.6802, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 14.920937329732816, | |
| "learning_rate": 8.382180034472353e-06, | |
| "loss": 1.3365, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 14.938434249442729, | |
| "learning_rate": 3.5261371521817247e-06, | |
| "loss": 1.173, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 14.471664148153287, | |
| "learning_rate": 5.234682881719766e-07, | |
| "loss": 1.0972, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9850746268656716, | |
| "eval_loss": 1.7861212491989136, | |
| "eval_runtime": 0.7107, | |
| "eval_samples_per_second": 5.628, | |
| "eval_steps_per_second": 1.407, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9850746268656716, | |
| "step": 33, | |
| "total_flos": 13714367447040.0, | |
| "train_loss": 1.5271921013340806, | |
| "train_runtime": 363.6097, | |
| "train_samples_per_second": 47.122, | |
| "train_steps_per_second": 0.091 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 13714367447040.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |